Traffic data simulator

• US 9,368,027 B2
• Filed: 02/06/2014
• Issued: 06/14/2016
• Est. Priority Date: 11/01/2013
• Status: Active Grant

• Current Assignee: HERE Global B.V. (Nokia Corporation)
• Original Assignee: HERE Global B.V. (Nokia Corporation)
• Inventors: Jang, Dongwook, Arcot, Praveen, Ernster, Marcus
• Primary Examiner(s): MARC-COLEMAN, MARTHE Y
• Application Number:
  US14/174,307
• Publication Number:
  US 20150127245A1
• Time in Patent Office: 859 Days
• Field of Search: 701117-119, 701/414, 340/995.14, 340/995.19, 382/104
• US Class Current: 1/1
• CPC Class Codes: G08G 1/0112 from the vehicle, e.g. floating car data [FCD]
• CPC Class Codes: G08G 1/0116 from roadside infrastructure, e.g. beacons
• CPC Class Codes: G08G 1/0129 for creating historical data or processing based on historical data
• CPC Class Codes: G08G 1/0133 for classifying traffic situation
• CPC Class Codes: G08G 1/0145 for active traffic flow control
• CPC Class Codes: G08G 1/0962 having an indicator mounted inside the vehicle, e.g. giving voice messages
• CPC Class Codes: G09B 29/003 Maps

Abstract

In one embodiment, traffic data that originates from sensors, cameras, or observations is analyzed. The traffic data is associated with multiple repeating time epochs or intervals. The traffic data is divided into clusters using a clustering technique. The traffic data may be collected on specific days such as holidays. The holiday traffic data may be divided data into clusters and a dominant traffic pattern cluster that represents a holiday classification is identified. The dominant traffic pattern cluster is stored in a traffic prediction model.

Claims

1. A method comprising:

receiving sensor data representing traffic patterns from one or more sensors;

identifying holiday traffic data from the sensor data, the holiday traffic data associated with multiple repeating time epochs for multiple holidays;

calculating a plurality of clusters for the holiday traffic data, wherein at least one of the plurality of clusters is defined by a variable centroid;

identifying a dominant traffic pattern cluster from the plurality of clusters; and

storing the dominant traffic pattern cluster in a traffic prediction model,

wherein a road layout or a traffic signal pattern is tested using simulated traffic data generated from the traffic prediction model and the dominant traffic pattern cluster.

2. The method of claim 1, wherein the dominant traffic pattern cluster is a first dominant traffic pattern cluster, the method further comprising:

identifying a second dominant traffic pattern cluster; and

storing the second dominant traffic pattern cluster in the traffic prediction model.

3. The method of claim 2, wherein the first dominant traffic pattern cluster corresponds to major holidays and the second dominant traffic pattern cluster corresponds to minor holidays.

4. The method of claim 1, further comprising:

receiving a request for traffic data;

accessing a lookup table to determine whether a current day is a normal day or a holiday;

when the current day is a holiday, generating a traffic prediction based on the first dominant traffic pattern cluster in a traffic prediction model.

5. The method of claim 1, further comprising:

receiving a holiday time epoch and a road segment identifier; and

accessing the traffic prediction model in response to the holiday time epoch.

6. The method of claim 1, further comprising:

performing a filtering algorithm on the holiday traffic data to remove outlier data points.

7. The method of claim 6, wherein the filtering algorithm is coded in an object-oriented programming language.

8. The method of claim 1, further comprising:

filtering the dominant traffic pattern cluster to remove outlier data points.

9. The method of claim 1, further comprising:

calculating, by a processor, an average value and a standard deviation value for the dominant traffic pattern cluster;

receiving a request for traffic data; and

providing the average value and the standard deviation value for one or more of the clusters in response to the request for traffic data.

10. The method of claim 1, wherein dividing into clusters comprises:

selecting, using a random algorithm, an initial centroid for each of the plurality of clusters;

assigning additional traffic data to the initial centroids; and

calculating subsequent centroids based on averages of the additional traffic data and the initial centroids.

11. The method of claim 10, further comprising:

comparing a difference in location between one of the initial centroids and a corresponding one of the subsequent centroids to the threshold.

12. An apparatus comprising:

at least one processor; and

at least one memory including computer program code for one or more programs,

the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following,

receiving holiday traffic data from one or more sensors;

dividing the holiday traffic data into clusters;

identifying a first dominant traffic pattern cluster corresponding to major holidays;

identifying a second dominant traffic pattern cluster corresponding to minor holidays;

receiving a request for traffic that indicates a holiday date; and

accessing either the first dominant traffic pattern cluster or the second dominant traffic pattern cluster depending on whether the holiday data in a major holiday or a minor holiday,

wherein a road layout or a traffic signal pattern is tested using simulated traffic data generated from the first dominant traffic pattern cluster or the second dominant traffic pattern cluster.

13. The apparatus of claim 12, further comprising:

storing the first dominant traffic pattern cluster and the second dominant traffic pattern cluster in a traffic prediction model.

14. The apparatus of claim 12, further comprising:

identifying a third dominant traffic pattern cluster corresponding to sub-minor holidays.

15. The apparatus of claim 12, wherein the major holidays and minor holidays are defined according to geographic location.

16. The apparatus of claim 12, wherein the request for traffic includes a time epoch and a road segment identifier, wherein the first dominant traffic pattern cluster or the second dominant traffic pattern cluster are accessed according to the time epoch and the road segment identifier.

17. The apparatus of claim 12, wherein the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following,

performing a filtering algorithm on the holiday traffic data to remove outlier data points.

18. The apparatus of claim 12, wherein the filtering algorithm is coded in an object-oriented programming language.

19. A non-transitory computer readable medium including instructions that when executed are operable to:

receive sensor data from one or more sensors;

identify holiday traffic data measured in the sensor data, wherein the holiday traffic data is organized into time intervals;

divide the measured holiday traffic data within the time intervals into data clusters, wherein the data clusters are variably defined using a clustering technique according to a list of holiday classifications;

calculate statistical parameters of the measured traffic data within the time intervals, wherein simulated traffic data is generated based on the statistical parameters,

receive a request for a traffic prediction including a holiday classification; and

access the data clusters based on the holiday classification,

wherein a road layout or a traffic signal pattern is tested using the simulated traffic data.